- Home
- Skills
- Williamzujkowski
- Cognitive Toolworks
- Quality Standards Analyzer
quality-standards-analyzer_skill
- Python
5
GitHub Stars
3
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill williamzujkowski/cognitive-toolworks --skill quality-standards-analyzer- CHANGELOG.md1.6 KB
- index-entry.json805 B
- SKILL.md8.8 KB
Overview
This skill assesses code quality across eight-plus languages using a mix of language-agnostic principles and language-specific best practices. It produces a scored report with actionable issues, diff-ready fixes for mechanical problems, and prioritized guidance for manual review. It is designed for pre-merge checks, baseline standardization, and developer training in multi-language codebases.
How this skill works
The analyzer first validates inputs and detects language via extension, shebangs, and syntax patterns if language is not provided. It applies universal rules (DRY, SOLID thresholds, naming, magic numbers, documentation) to generate a quick score, then optionally runs language-specific rules mapped to official style guides and produces diffs or manual-review items. Final output is a JSON report with score, issues, metrics, and a timestamp normalized to America/New_York (NOW_ET).
When to use it
- Run before merging pull requests to enforce consistent quality gates
- Establish baseline standards for repositories with mixed languages
- Automate pre-commit or CI code review workflows
- Train teams on both language-agnostic and language-specific best practices
- Audit codebases for maintainability and documentation gaps
Best practices
- Provide explicit language when auto-detection confidence is below 80%
- Set ruleset to 'both' for comprehensive checks, or 'universal' for fast validation
- Use severity_threshold to focus reports on actionable items in CI
- Integrate generated diffs into automated formatting tools before manual review
- Split very large files (>10k lines) to avoid fail-fast conditions
Example use cases
- CI job that runs the analyzer on changed files and blocks merging on score < 70
- Repository-wide baseline scan to create a remediation backlog for multiple languages
- Pre-merge check that auto-fixes import ordering and formatting while surfacing architecture issues
- Developer training session that uses reported issues to teach PEP 8, Effective Go, and Airbnb JS conventions
- Tooling integration that produces ESLint/Pylint/Clippy config suggestions from detected violations
FAQ
Supported languages include Go, JavaScript, Kotlin, Python, Rust, Shell, Swift, TypeScript, and auto-detection for mixed directories.
Can the analyzer fix all issues automatically?
No. Mechanical issues like formatting and import order can get diff-ready fixes; logic or architecture problems are surfaced as manual-review items.